Anomalies are patterns in the data that do not conform to a well-defined notion of normal behaviour.
Techniques used to detection anomalies typically require training before using on new data.
This Jupyter Notebook reproduces the results from Oana Niculaescu's article in XRDS, Applying Data Science for Anomaly and Change Point Detection.
To start Jupyter Notebook in background (will open browser):
nice jupyter-notebook &
To stop Jupyter notebooks:
jupyter-notebook stop
To output a notebook as PDF or LaTeX:
jupyter nbconvert --exec --to latex --template article.tplx [your-notebook.ipynb]
To further customise output of a notebook, see